Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1098 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.3059. Min Range: -14.3059
Max Act: 14.3059. Min Act: -0.1700
Data Index: 2590658 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.3059. Min Range: -14.3059
Max Act: 14.2434. Min Act: -0.1700
Data Index: 5130345 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.3059. Min Range: -14.3059
Max Act: 14.1809. Min Act: -0.1700
Data Index: 5570978 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.3059. Min Range: -14.3059
Max Act: 14.1809. Min Act: -0.1700
Data Index: 5667956 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.3059. Min Range: -14.3059
Max Act: 14.1184. Min Act: -0.1700
Data Index: 3702263 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8684. Min Act: -0.1700
Data Index: 820422 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 4829196 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 6395479 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 5837089 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 2214295 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 8678652 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9934. Min Act: -0.1700
Data Index: 3991250 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 4570451 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.9309. Min Act: -0.1700
Data Index: 8345471 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8684. Min Act: -0.1700
Data Index: 8591040 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8684. Min Act: -0.1700
Data Index: 1092008 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8684. Min Act: -0.1700
Data Index: 8007247 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8059. Min Act: -0.1700
Data Index: 1681753 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.8684. Min Act: -0.1700
Data Index: 4101474 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.3059. Min Range: -14.3059
Max Act: 13.7434. Min Act: -0.1700
Data Index: 8210757 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19